ClawHub
Back to skill

Security audit

UXC Context7

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps an agent query Context7 documentation and does not show hidden or destructive behavior.

Before installing, confirm you are comfortable with the agent using the uxc skill to create a context7-mcp-cli command link and sending documentation queries to the external Context7 MCP service. The included validation script appears to be for maintainers and only reads expected skill package files.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The declared description says the skill is used to retrieve current library documentation and code examples via Context7 MCP. The supplied code chunk instead implements a local lint/validation script for the skill package itself. It verifies required files, frontmatter, specific command examples, forbidden patterns, and minimum YAML fields. Although it references Context7 commands and endpoint text, it only checks that documentation contains those strings; it does not perform documentation queries, fetch version-specific content, or provide examples from Context7. This is a materially different primary purpose, so it is a mismatch.

Static analysis

No suspicious patterns detected.